Detection and Identification of Bad Data Based on Neural Network and K-means Clustering

Zhang, Tong; Wang, Yi; Ning, Jian Rong; Zhai, Mingyu

doi:10.1109/isgt-asia.2019.8881625

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…determined empirically after several attempts. In accordance with[38][39], we noticed that smaller structures with a smaller number of hidden layers and neurons could not reach a good training accuracy even after large training times, since they were not capable of extracting the relevant feature from the data set. On the contrary, bigger structures showed high training accuracy but experienced overfitting problems and performed poorly outside the training set during the test phase.…”

supporting

confidence: 60%

“…To demonstrate the TI algorithm, a bad data detection and identification algorithm, and a state estimator are coupled with the proposed method. For this purpose, a modified version of the algorithm introduced in [37] is used as a bad data detection and identification algorithm even though others methods can be used, e.g., [38] and [39]. Once the measurement set has been checked and possibly modified, the topology configuration is estimated, and subsequently, a network state estimation is performed using an UKF.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inertia Estimation of a Power System Area Based on Iterative Equation Error System Identification

Gotti,

Bizzarri,

Brambilla

et al. 2024

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

por el privilegio de cursar mis estudios doctorales con una financiación, a pesar de la incertidumbre de los últimos tiempos. En este sentido, quiero expresar un agradecimiento particular al profesor Santiago Arnaltes por estar involucrado en el proceso de búsqueda de la beca.Quisiera también expresar mi gratitud a mis directores de tesis por haberme permitido ingresar al programa y darme la oportunidad de realizar esta experiencia enriquecedora. Los consejos recibidos en estos años sobre la redacción y la estructura de los artículos han sido muy valiosos.Considero necesario reconocer a los profesores Juan Carlos Burgos y Mónica Chinchilla el interés, la ayuda y los consejos recibidos durante la preparación de las prácticas de sus asignaturas.Un ringraziamento doveroso va al gruppo del Politecnico di Milano che mi ha ospitato durante i 3 mesi del periodo di ricerca all'"estero". In particolare, vorrei esprimere la mia gratitudine a Federico Bizzarri e ad Angelo Brambilla per i preziosi consigli elargiti durante le riunioni e le videochiamate; grazie per mostrarmi dove fissare l'asticella. Sulla falsariga di una frase che scrissi circa nove anni fa in una circostanza simile a questa, ritengo di dover ringraziare anche il mio paese, l'Italia, che, seppur non priva di difetti, mi ha dato l'opportunità di ricevere una formazione di primo livello. Indipendentemente da quello che il futuro ha in serbo per me, le sarò sempre grato.Finalmente, quiero dar las gracias a Lourdes, por su apoyo incondicional, por ayudarme a tomar conciencia de mí mismo, por poner la vida en perspectiva y, simplemente, por ser ella.

show abstract

supporting

confidence: 60%

Section: Introductionmentioning

confidence: 99%

Inertia Estimation of a Power System Area Based on Iterative Equation Error System Identification

Gotti,

Bizzarri,

Brambilla

et al. 2024

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

show abstract

“…The measurement vector z is a nonlinear function [24,25] of the state vector x and can be expressed as…”

Section: System Model 21 Measurement Modelmentioning

confidence: 99%

Smart Grid Outlier Detection Based on the Minorization–Maximization Algorithm

Qiao,

Gao,

et al. 2023

Sensors

View full text Add to dashboard Cite

Outliers can be generated in the power system due to aging system equipment, faulty sensors, incorrect line connections, etc. The existence of these outliers will pose a threat to the safe operation of the power system, reduce the quality of the data, affect the completeness and accuracy of the data, and thus affect the monitoring analysis and control of the power system. Therefore, timely identification and treatment of outliers are essential to ensure stable and reliable operation of the power system. In this paper, we consider the problem of detecting and localizing outliers in power systems. The paper proposes a Minorization–Maximization (MM) algorithm for outlier detection and localization and an estimation of unknown parameters of the Gaussian mixture model (GMM). To verify the performance of the method, we conduct simulation experiments by simulating different test scenarios in the IEEE 14-bus system. Numerical examples show that in the presence of outliers, the MM algorithm can detect outliers better than the traditional algorithm and can accurately locate outliers with a probability of more than 95%. Therefore, the algorithm provides an effective method for the handling of outliers in the power system, which helps to improve the monitoring analyzing and controlling ability of the power system and to ensure the stable and reliable operation of the power system.

show abstract

“…To demonstrate the TI algorithm, a bad data detection and identification algorithm, and a state estimator are coupled with the proposed method. For this purpose, a modified version of the algorithm introduced in [11] is used as a bad data detection and identification algorithm even though others methods can be used, e.g., [12] and [13]. Once the measurement set has been checked and possibly modified, the topology configuration is estimated, and subsequently, a network state estimation is performed using an unscented Kalman filter (UKF).…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network Approach for Online Topology Identification in State Estimation

Gotti

Amarís

Ledesma

2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

This paper introduces a network topology identification (TI) method based on deep neural networks (DNNs) for online applications. The proposed TI DNN utilizes the set of measurements used for state estimation to predict the actual network topology and offers low computational times along with high accuracy under a wide variety of testing scenarios. The training process of the TI DNN is duly discussed, and several deep learning heuristics that may be useful for similar implementations are provided. Simulations on the IEEE 14-bus and IEEE 39-bus test systems are reported to demonstrate the effectiveness and the small computational cost of the proposed methodology.

show abstract

Detection and Identification of Bad Data Based on Neural Network and K-means Clustering

Cited by 6 publications

References 8 publications

Inertia Estimation of a Power System Area Based on Iterative Equation Error System Identification

Inertia Estimation of a Power System Area Based on Iterative Equation Error System Identification

Smart Grid Outlier Detection Based on the Minorization–Maximization Algorithm

A Deep Neural Network Approach for Online Topology Identification in State Estimation

Contact Info

Product

Resources

About